Google Research unveiled TurboQuant, a novel quantization algorithm that compresses large language models’ Key-Value caches ...

Learn how to compress images and JPEG files to reduce file size, speed up your website and maintain image quality.

A research team has developed a Gaussian Splatting processing platform that supports end-to-end processing from data acquisition to multi-platform rendering. Their framework provides a solid ...

Researchers have developed a dynamic range compression dual-domain attention network for enhancing tunnel images under extreme exposure conditions, a problem that continues to challenge transportation ...

P-n diodes are two-terminal devices that consist of two types of semiconductor materials (i.e., a p-type and an n-type ...

Training a large artificial intelligence model is expensive, not just in dollars, but in time, energy, and computational ...

NVIDIA researchers have proposed a neural compression method for material textures that enables random-access lookups and ...

Intel TSNC brings neural texture compression with up to 18x reduction, faster decoding, and flexible SDK support for modern ...

NVIDIA showcases Neural Texture Compression at GTC 2026, cutting VRAM usage by up to 85% with real-time AI reconstruction.

Neural Texture Compression (NTC) could be a game-changer on par with DLSS if it can reduce the VRAM requirement for textures ...

In its "Tuscan Wheels" demo, the company showed VRAM usage dropping from roughly 6.5GB with traditional BCN-compressed ...